Swarm

Fan out N parallel rlm.spawn workers. They may cover separate slices, race the same brief, or mix both. The parent waits, aggregates, and returns one report.

Start

Open a todo list in your reply with one entry per phase before launching anything.

1. Frame
2. Fan out
3. Aggregate
4. Report

Phase A: Frame

1. State the done predicate and the artifact or report the swarm must return.
2. Choose the shape. Partition into slices, race N workers on identical briefs, or mix both. For a race or mixed shape, declare first pass, rank all, or best-of before spawning.
3. Set N from the user or derive it from the shape. N is total workers. Keep it under the parent inbox limit (20 pending replies) or have workers write reports to files.
4. Pick the worker model from swarm workers in the injected pstack role table when present. Otherwise use zai/glm-5.3. For a model race, name each arm's model up front.
5. Give each worker its own writable output when it writes.

Phase B: Fan out

Spawn all N workers in one ipython cell, one rlm.spawn(brief, name=<unique>, model=<configured or omitted>) each, then end the turn. Replies arrive as agent messages; a worker that writes a report to disk names the path in its reply.

When a worker must start from a non-default branch, tell it the branch and give it its own worktree (git worktree add).

Every brief stands alone. Include the goal, scope, exact slice or race arm, how to verify, and what to report. Reports use PASS, ISSUES, or BLOCKED with evidence.

If a worker drops out, proceed with N-1 and note it.

Phase C: Aggregate

Read the replies (await rlm.collect(handles, timeout_ms=0) for status, the agent messages or report files for content). For coverage, every required slice needs a result. For a race, apply the selection rule declared up front. Use first pass, rank all, or best-of. Do not paste raw worker dumps.

Keep a compact result table, one-line evidenced issues, and explicit gaps or dropouts.

Phase D: Report

Return one consolidated in-chat report with the table, issue one-liners, gaps or dropouts, and the race rule when used.